What is react-native-mcp AGENTS.md?

Project instructions for an MCP server that helps AI assistants develop and test React Native mobile apps.

They are for working with iOS and Android devices, Metro and the Hermes runtime, builds, tests, linting, type checks, and MCP tools.

They give contributors the commands, architecture, rules, and known error format needed to work on the repository correctly.

How luizhbesper/react-native-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to luizhbesper/react-native-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/luizhbesper/react-native-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/luizhbesper/react-native-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/luizhbesper/react-native-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/luizhbesper/react-native-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/luizhbesper/react-native-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/luizhbesper/react-native-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/luizhbesper/react-native-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/luizhbesper/react-native-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 729 This file is loaded in full into every session.

When invoked 729 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00729	$0.00729
Opus 5.5	$0.00292	$0.00292
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 2mo ago against content hash 076fa9c930c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

react-native-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working on this repository (react-native-dev-mcp — an MCP server for React Native development).

Commands

pnpm install              # setup (pnpm 10+, Node 22+)
pnpm test                 # vitest unit suites — must pass before any commit
pnpm lint                 # biome (format + lint); pnpm lint:fix to autofix
pnpm typecheck            # tsc --noEmit
pnpm build                # tsdown → dist/index.mjs
node scripts/mcp-call.mjs <tool> '<json>'   # call any tool against the built server

Architecture in 30 seconds

src/tools/registry.ts — defineTool(); every tool is defined with zod in/out schemas, annotations, a spec id, and an optional capability gate. Start here.
src/env/ — startup capability detection; drives which tools get registered (spec 002).
src/devices/ — facade.ts routes unified device ids to backends/simctl.ts (iOS) or backends/adb.ts (Android).
src/metro/ — CDP bridge to the app's Hermes runtime via Metro's /json/list: console ring buffer, evaluate_js (promise polling workaround — Hermes lacks awaitPromise), reload.
src/build/ — background build jobs + the YAML signature DB (signatures/*.yaml) that parses native build logs into diagnostics.

Hard rules

Spec-first. Tool contracts live in specs/NNN-*.md. Changing tool behavior means changing the spec in the same PR. Acceptance criteria map 1:1 to vitest case names.
stdout is the MCP transport. Never console.log in src/ — use src/shared/logger.ts (stderr, gated by --verbose).
No shell strings from inputs. All toolchain calls go through src/shared/exec.ts with argv arrays. For adb shell, quote with shellQuote().
Tests must not require Xcode or the Android SDK. Mock through the exec seam with fixtures in test/fixtures/. Real-device suites live in test/integration/ behind RUN_SIMULATOR_TESTS/RUN_ANDROID_TESTS env vars.
Token budgets are part of every contract (spec 000): short text summary + structuredContent; lists capped; raw logs go to disk, return the path.
Error envelope: failures the model can act on are isError: true results with {code, message, remediation} — codes are registered in src/shared/errors.ts.

Read the full file on GitHub · 57 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 57 lines · 729 tokens per session scan A 076fa9c930c2

Subscribe to this mod's changes

react-native-mcp AGENTS.md is an instructions file published in the GitHub repository luizhbesper/react-native-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 729 tokens to every session, about $0.0029 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-agents claude developer-tools expo hermes mcp

react-native-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
react-native-mcp AGENTS.mdluizhbesper/react-native-mcp	Instructions file	2	4mo ago	MIT	A	729	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

react-native-mcp: Instructions file for Codex